Diffusion (Large) Language Models (dLLMs) now match the downstream performance of their autoregressive counterparts on many tasks, while holding the promise of being more efficient during inference. One critical design aspect of dLLMs is the \textit{sampling procedure} that selects which tokens to unmask at each diffusion step. Indeed, recent work has found that heuristic strategies such as confidence thresholding improve both sample quality and token throughput compared to random unmasking. However, such heuristics have downsides: they require manual tuning, and we observe that their performance degrades with larger block sizes. In this work, we instead propose to train sampling procedures using reinforcement learning. Specifically, we formalize masked diffusion sampling as a Markov decision process in which the dLLM serves as the environment, and propose a lightweight policy based on a single-layer transformer that maps dLLM token confidences to unmasking decisions. Our experiments show that these trained policies match the performance of state-of-the-art heuristics when combined with semi-autoregressive (block) generation, while outperforming them in the full-diffusion setting.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
While Large Language Models (LLMs) possess strong reasoning capabilities, enabling them to learn continuously from experience without parametric retraining remains an open challenge. Existing Retrieval-Augmented Generation (RAG) approaches typically treat memory as a static or append-only corpus, leading to "memory saturation''---where accumulating noise and redundant information degrade performance over time. To address this, we propose an Experience Risk Minimization (ERM) framework that formalizes the experience library as a learnable parameter under an explicit capacity budget. We introduce Textual Stochastic Gradient Descent (TSGD), a discrete optimization algorithm that refines this library via failure-driven Add, Edit, and Delete operations. TSGD estimates ``textual gradients'' through self-reflection and employs a dual-verification mechanism to ensure generalization, effectively preventing overfitting to local errors. Empirical results on MATH and AIME benchmarks demonstrate that TSGD achieves state-of-the-art performance, improving accuracy by up to 18.7\% over zero-shot baselines and significantly outperforming static RAG, all while maintaining a compact memory footprint (compressing hundreds of experiences into $\approx$30 high-utility rules).
Applications · Chemistry, Physics, and Earth Sciences
Discovering heterogeneous catalysts tailored for specific reaction intermediates remains a fundamental bottleneck in materials science. While traditional trial-and-error methods and recent generative models have shown promise, they struggle to capture the intrinsic coupling between surface geometry and adsorbate interactions. To address this limitation, we propose CatFlow, a flow matching-based framework for de novo design and structure prediction of heterogeneous catalysts. Our model operates on a primitive cell-based factorized representation of the slab-adsorbate complex, reducing the number of learnable variables by an average of 9.2x while explicitly encoding the surface orientation of the slab-adsorbate interface. Experiments on the Open Catalyst 2020 dataset demonstrate that CatFlow significantly improves the structural fidelity of generated catalysts compared to autoregressive and sequential baselines. Further experiments show that the generated structures accurately capture the adsorption energy distributions of physically plausible interfaces and lie closer to thermodynamic local minima.
Applications · Robotics
Large and diverse datasets are needed for training generalist robot policies that have potential to control a variety of robot embodiments--robot arm and gripper combinations--across diverse tasks and environments. As re-collecting demonstrations and retraining for each new hardware platform are prohibitively costly, we show that existing robot data can be augmented for transfer and generalization. The Open X-Embodiment (OXE) dataset, which aggregates demonstrations from over 60 robot datasets, has been widely used as the foundation for training generalist policies. However, it is highly imbalanced: the top four robot types account for over 85% of its real data, which risks overfitting to robot--scene combinations. We present AugE-Toolkit, a scalable robot augmentation pipeline, and OXE-AugE, a high-quality open-source dataset that augments OXE with 9 different robot embodiments. OXE-AugE provides over 4.4 million trajectories, more than triple the size of the original OXE. We conduct a systematic study of how scaling robot augmentation impacts cross-embodiment learning. Results suggest that augmenting datasets with diverse arms and grippers improves policy performance not only on the augmented robots, but also on unseen robots and even the original robots under distribution shifts. In physical experiments, we demonstrate that generalist policies such as OpenVLA and $\pi_0$ benefit from fine-tuning on OXE-AugE, improving success rates by 24-45% on previously unseen robot-gripper combinations across four real-world manipulation tasks.
Deep Learning · Generative Models and Autoencoders
Steering intermediate representations has emerged as a powerful strategy for controlling generative models. However, despite its empirical success, it currently lacks a comprehensive theoretical framework. In this paper, we bridge this gap by formalizing the theory of concept steering. First, we establish a link between steering and affine concept erasure, proving that the standard approach for removing unwanted behaviors is a special case of LEACE (a closed-form method for affine erasure). Next, we formulate a principled theoretical framework for concept switching, LEACE-Switch, and characterize the assumptions under which it provides an optimal affine solution. Building on this analysis, we then introduce MidSteer (Minimal Disturbance concept Steering), a more general affine framework for concept manipulation that relaxes these assumptions and enables directed, minimal-disturbance transformations. We empirically demonstrate that MidSteer performs favorably across a range of tasks, modalities, and architectures, including vision diffusion models and large language models.
General Machine Learning · Representation Learning
Multi-view classifiers typically fuse all observed views into a single representation, which becomes fragile when some views are missing or corrupted.We propose a prototype-anchored fusion module based on an entropically regularized unbalanced optimal transport (UOT) barycenter.Each view is summarized into a small set of learned atoms and is matched to a shared prototype support; fusion outputs a probability measure over prototypes with fixed dimension.By relaxing marginal constraints with a generalized KL penalty, the UOT objective can leave a fraction of view mass unmatched when matching is geometrically costly, yielding a simple differentiable trimming mechanism without hand-tuned thresholds.We provide a basic theoretical result showing that discarding an arbitrary subset of atom mass incurs a penalty bounded by its total mass, independent of transport distances.Experiments on multi-view action recognition benchmarks under simulated missing views, missing-rate shift, and feature-space corruption demonstrate consistently improved stability under severe missingness with modest overhead on top of strong backbones.
Deep Learning · Algorithms
In this paper, we present CAT-Q, **C**ost-efficient and **A**ccurate **T**ernary **Q**uantization, to compress LLMs. Unlike current state-of-the-art ternary quantization methods that rely on data-intensive and costly quantization-aware training to mitigate severe performance degradation, CAT-Q employs a simple yet effective post-training quantization scheme, thereby is easily applicable to LLMs with diverse architectures and model sizes. It has two key components, learnable modulation (LM) and softened ternarization (ST), which are coupled from an optimization perspective. LM leverages a composition of learnable factors to modulate the distribution of high-precision weights and the ternary threshold, making them less sensitive to ternarization. ST further introduces a novel transition function to guide the ternarization process toward stable convergence. We show that, for pre-trained LLMs with 1.7B to 8B parameters, CAT-Q can quantize them into ternary models using merely 512 calibration samples, while achieving competitive performance to the seminal BitNet 1.58-bit v1 and v2 families (with 1.3B to 7B parameters) trained with 100B tokens, yielding about a 100,000x reduction in training tokens. Moreover, we show for the first time that CAT-Q can quantize even larger pre-trained LLMs having 14B to 235B parameters into leading ternary models within 8 to 60 hours on 8 A100-80GB GPUs. Code will be made publicly available.
Deep Learning · Large Language Models
Standard preference alignment relies on a binary forced-choice paradigm, assuming definitive preferences for all pairs. However, we find that indistinguishable pairs are prevalent even in standard benchmarks, where quality differences of two responses often fall below the labeler's discriminative resolution limit. Forcing a choice in such cases could inject significant noise that undermines policy optimization. In this work, we propose a silent-aware framework that introduces a principled way to allow annotators to stay silent (i.e., express ties) and then explicitly model these ties during optimization. Our findings reveal a compelling phenomenon: when ties are properly modeled, supervision from small models yields alignment surpassing that of forced-choice LLMs or human experts. This discovery highlights a cost-effective path for alignment: respecting a labeler’s resolution limit is more critical than increasing its capability, while simultaneously unlocking the latent value in existing benchmarks by properly modeling inherent tie signals without requiring any re-labeling effort. To leverage these signals, we propose several optimization objectives to drive the policy toward high-reward regions while mitigating unreliable updates that lead to arbitrary distribution shifts. Our approaches significantly surpass conventional alignment performance, consistently outperforming the strongest available baselines across diverse benchmarks.
Deep Learning · Algorithms
In this paper, we present CAT-Q, **C**ost-efficient and **A**ccurate **T**ernary **Q**uantization, to compress LLMs. Unlike current state-of-the-art ternary quantization methods that rely on data-intensive and costly quantization-aware training to mitigate severe performance degradation, CAT-Q employs a simple yet effective post-training quantization scheme, thereby is easily applicable to LLMs with diverse architectures and model sizes. It has two key components, learnable modulation (LM) and softened ternarization (ST), which are coupled from an optimization perspective. LM leverages a composition of learnable factors to modulate the distribution of high-precision weights and the ternary threshold, making them less sensitive to ternarization. ST further introduces a novel transition function to guide the ternarization process toward stable convergence. We show that, for pre-trained LLMs with 1.7B to 8B parameters, CAT-Q can quantize them into ternary models using merely 512 calibration samples, while achieving competitive performance to the seminal BitNet 1.58-bit v1 and v2 families (with 1.3B to 7B parameters) trained with 100B tokens, yielding about a 100,000x reduction in training tokens. Moreover, we show for the first time that CAT-Q can quantize even larger pre-trained LLMs having 14B to 235B parameters into leading ternary models within 8 to 60 hours on 8 A100-80GB GPUs. Code will be made publicly available.
Deep Learning · Large Language Models
Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptimization, in which policy models overfit to the reward model, exploit spurious reward patterns instead of faithfully capturing human intent. Prior mitigations primarily relies on surface semantic information and fails to efficiently address the misalignment between the reward model (RM) and the policy model caused by continuous policy distribution shifts. This inevitably leads to an increasing reward discrepancy, exacerbating reward overoptimization. To address these limitations, we introduce R2M (Real-Time Aligned Reward Model), a novel lightweight RLHF framework. R2M goes beyond vanilla reward models that solely depend on the semantic representations of a pretrained LLM. Instead, it leverages the evolving hidden states of the policy (namely policy feedback) to align with the real-time distribution shift of the policy during the RL process. This work points to a promising new direction for improving the performance of reward models through real-time utilization of feedback from policy models.
Deep Learning · Large Language Models
The deployment of Large Language Models is constrained by the memory and bandwidth demands of static weights and dynamic Key-Value cache. SVD-based compression provides a hardware-friendly solution to reduce these costs. However, existing methods suffer from two key limitations: some are suboptimal in reconstruction error, while others are theoretically optimal but practically inefficient. In this paper, we propose Swift-SVD, an activation-aware, closed-form compression framework that simultaneously guarantees theoretical optimum, practical efficiency and numerical stability. Swift-SVD incrementally aggregates covariance of output activations given a batch of inputs and performs a single eigenvalue decomposition after aggregation, enabling training-free, fast, and optimal layer-wise low-rank approximation. We employ effective rank to analyze local layer-wise compressibility and design a dynamic rank allocation strategy that jointly accounts for local reconstruction loss and end-to-end layer importance. Extensive experiments across six LLMs and eight datasets demonstrate that Swift-SVD outperforms state-of-the-art baselines, achieving optimal compression accuracy while delivering 3–70$\times$ speedups in end-to-end compression time. Our code will be released upon acceptance.
Applications · Health / Medicine
Vision-language models (VLMs) combining reinforcement learning (RL) ignite remarkable progress in multimodal reasoning, yet still struggle with medical images, which typically exhibit extremely sparse visual evidence to inform clinical decision-making. We recognize that pruning visual tokens outside the grounding region greatly enhances medical reasoning. However, a united RL framework for active visual token pruning (VTP) and medical multimodal reasoning remains unestablished. Here, we propose a dual-stream RL framework, ViToS, to fulfill token pruning and question answering. ViToS trains one policy model with two task branches, where one focuses on grounding while the other conducts token-sparse reasoning after VTP. Furthermore, we solve the coupled policy learning problem by introducing the cross-feedback sequential optimization, avoiding gradient conflict and facilitating convergence of the shared policy model. Evaluated on seven medical benchmarks, our method reduces visual tokens to 77\% of the original sequence length while achieving a 108.27\% relative performance on Lingshu-7B and 104.16\% relative performance on HuatuoGPT-Vision-7B. Overall, ViToS delivers superior performance and inference speedup, establishing an efficient paradigm for medical multimodal reasoning.
Deep Learning · Large Language Models
Pre-training large language models from scratch is prohibitively expensive as model scales increase. A practical alternative is Model Width Expansion (MWE), which grows a larger model from a well-pretrained ''seed'' model to inherit existing capabilities at initialization. However, we identify a phenomenon termed the _**Subspace Trap**_: during continual pre-training, parameter updates largely stagnate within a low-dimensional subspace aligned with the initialization, limiting the effective capacity of the expanded model. Our theoretical analysis investigates this issue by attributing it to the function-preserving properties of width expansion. In particular, element-wise adaptive optimizers remain confined to the trap, whereas optimizers that yield an isotropic geometry of parameter updates can escape. To demonstrate the impact of the subspace trap on model performance, we conduct empirical experiments across different model sizes and model families, which show that escaping the trap is principally effective in improving training efficiency and overall model performance. Detailed mechanistic analyses further confirm that escaping the trap indeed activates the new dimensions to encode general knowledge. Our code is available at https://anonymous.4open.science/r/MWE-1B46.
Probabilistic Methods · Everything Else
Evaluating conditional coverage remains one of the most persistent challenges in assessing the reliability of predictive systems. Although conformal methods can give guarantees on marginal coverage, no method can guarantee to produce sets with correct conditional coverage, leaving practitioners without a clear way to interpret local deviations. To overcome sample-inefficiency and overfitting issues of existing metrics, we cast conditional coverage estimation as a classification problem. Conditional coverage is violated if and only if any classifier can achieve lower risk than the target coverage. Through the choice of a (proper) loss function, the resulting risk difference gives a conservative estimate of natural miscoverage measures such as L1 and L2 distance, and can even separate the effects of over- and under-coverage, as well as handle non-constant target coverages. We call the resulting family of metrics excess risk of the target coverage (ERT). We show experimentally that the use of modern classifiers provides much higher statistical power than simple classifiers underlying established metrics like CovGap. Additionally, we use our metric to benchmark different conformal prediction methods. Finally, we release an open-source package for ERT as well as previous conditional coverage metrics. Together, these contributions provide a new lens for understanding, diagnosing, and improving the conditional reliability of predictive systems.
Deep Learning · Large Language Models
Continual Pre-Training (CPT) is essential for enabling Language Models (LMs) to integrate new factual knowledge without erasing old. While classical CPT techniques like data replay have become the standard paradigm, the mechanisms underlying how LMs acquire and retain facts over time, termed as continual Factual Knowledge Acquisition (cFKA), remain unclear. In this work, we present a theoretical framework that characterizes the training dynamics of cFKA using a single-layer Transformer with linear attention, offering a unified explanation for the behavior of popular CPT methods. Our analysis reveals that regularization-based methods merely adjust the convergence rate of parameters without altering the inherent forgetting tendency, whereas data replay methods shift convergence dynamics and stabilize pretrained knowledge. Building on these insights, we propose a novel generative data replay approach, called Selecting Tokens via attentiOn Contribution (STOC), which identifies influential factual snippets to guide replay generation. Extensive experiments on both synthetic and real-world datasets validate our theoretical findings and demonstrate that STOC effectively enhances cFKA by mitigating catastrophic forgetting.
Deep Learning · Large Language Models
In real-world deployments of large language models (LLMs), balancing inference quality and computational cost has become a central challenge. Existing approaches tackle this trade-off along two largely independent dimensions: model routing, which switches among models of different scales to match request complexity, and test-time scaling (TTS), which adjusts inference-time compute within a fixed model for fine-grained control. However, this decoupled design introduces inherent limitations. Model routing yields coarse-grained, discrete performance changes due to the sparse set of model scales, while single-model TTS often encounters capacity ceilings and exhibits diminishing returns as compute increases. Moreover, treating the two mechanisms separately restricts adaptability in dynamic inference environments. To overcome these limitations, we introduce *Unified Inference Scaling (UIS)*, which unifies model routing and TTS in a single optimization space. Building on this formulation, we propose UniScale, an online framework that models adaptive UIS as a contextual multi-armed bandit problem and learns inference policies via LinUCB. The framework incorporates efficiency-aware learning and cost modeling to ensure stable and scalable optimization over high-dimensional action spaces. Evaluation shows that UniScale effectively exploits the synergy in the UIS space to deliver a fine-grained and consistently better quality-cost trade-off across diverse, dynamic inference scenarios.
Deep Learning · Large Language Models
Social simulation provides a compelling testbed for studying social intelligence, where agents interact through multi-turn dialogues under evolving contexts and strategically adapting opponents. Such environments are inherently non-stationary, requiring agents to dynamically adjust their strategies over time. However, most Large Language Model (LLM) based social agents rely on static personas, while existing approaches for enhancing social intelligence, such as offline reinforcement learning or external planners, are ill-suited to these settings, typically assuming stationarity and incurring substantial training overhead. To bridge this gap, we propose **ALSO** (**A**dversarial on**L**ine **S**trategy **O**ptimization), the first framework for online strategy optimization in multi-agent social simulation. ALSO advances social adaptation through two key contributions. (1) ALSO formulates multi-turn interaction as an adversarial bandit problem, where combinations of static personas and dynamic strategy instructions are treated as arms, providing a principled solution to non-stationarity without relying on environmental stability assumptions. (2) To predict rewards and generalize sparse feedback in multi-turn dialogues, ALSO introduces a lightweight neural surrogate to predict rewards from interaction histories, enabling sample-efficient exploration and continuous online adaptation. Experiments on the Sotopia benchmark demonstrate that ALSO consistently outperforms static baselines and existing optimization methods in dynamic environments, validating the effectiveness of adversarial online strategy optimization for building robust social agents. The codes of ALSO are available at https://anonymous.4open.science/r/ALSO-67D5/
Reinforcement Learning · Multi-agent
Large Language Models (LLMs) have rapidly advanced, with Gemini-3-Pro setting a new performance milestone. In this work, we explore collective intelligence as an alternative to monolithic scaling, and demonstrate that open-source LLMs' collaboration can surpass Gemini-3-Pro. We first revisit LLM routing and aggregation at scale and identify three key bottlenecks: (1) current train-free routers are limited by a query-based paradigm focusing solely on textual similarity; (2) recent aggregation methods remain largely static, failing to select appropriate aggregators for different tasks; (3) the complementarity of routing and aggregation remains underutilized. To address these problems, we introduce JiSi, a novel framework designed to release the full potential of LLMs' collaboration through three innovations: (1) Query-Response Mixed Routing capturing both semantic information and problem difficulty; (2) Support-Set-based Aggregator Selection jointly evaluating the aggregation and domain capacity of aggregators; (3) Adaptive Routing-Aggregation Switch dynamically leveraging the advantages of routing and aggregation. Comprehensive experiments on nine benchmarks demonstrate that JiSi can surpass Gemini-3-Pro with only 47% costs by orchestrating ten open-source LLMs, while outperforming mainstream baselines. It suggests that collective intelligence represents a novel path towards Artificial General Intelligence (AGI).
Test-time policy adaptation for multi-turn interactions (T$^2$PAM) is essential for aligning Large Language Models (LLMs) with dynamic user needs during inference time. However, existing paradigms commonly treat test-time adaptation as a single-axis problem, either purely refining instructions (Prompt Engineering) or only adjusting weights (Test-Time Training), ignoring that interaction failures stem from a coupled mix of ambiguity and incapacity. We argue that these two optimization paths are not merely additive but synergistic: semantic clarity acts as a pre-conditioner for effective parameter updates. To this end, we propose ROSA2, a framework that reformulates interaction as a joint optimization problem over the heterogeneous space of Words and Weights. By mathematically decomposing the error signal, ROSA2 utilizes textual gradients to rectify intent ambiguity and parameter updates to bridge capability gaps. Theoretically, we prove that this co-adaptation strictly reduces the required parameter shift for convergence. Empirically, ROSA2 outperforms state-of-the-art baselines by 30\% on MATH while reducing interaction turns by 40\%, demonstrating that refining the context unlocks the true potential of parameter updates.
Applications · Health / Medicine
Classifying protein topology is essential for deciphering biological function, but progress is held back by the lack of large-scale benchmarks that avoid duplicates and by models that do not scale well. We introduce TEDBench, a large-scale, non-redundant benchmark for protein fold classification constructed from the Encyclopedia of Domains (TED) and Foldseek-clustered AlphaFold structures. We show that on TEDBench, current protein representation learning methods either require very large models or fail to deliver strong performance. To address this challenge, we propose Masked Invariant Autoencoders (MiAE), a self-supervised framework for protein structure representation learning. MiAE uses an extremely high masking ratio of up to 90% with an $\mathrm{SE(3)}$-invariant encoder and a lightweight decoder that reconstructs backbone coordinates from the latent representation and mask tokens. MiAE scales well and outperforms supervised counterparts and state-of-the-art baselines on TEDBench, establishing a strong recipe for protein fold classification. To test transfer beyond AlphaFold structures, we further benchmark on a curated dataset from experimental structures of CATH 4.4. We will release TEDBench and model checkpoints.